© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56580
    Prev
    Next
    INDEX
    Explanations

    body parts (foot/feet)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĥ¸
    -0.10
    å·į
    -0.10
    å°½åĬĽ
    -0.09
    inz
    -0.09
    éŨæĪ·ç½ijç«Ļ
    -0.09
    rag
    -0.09
    大éŨ
    -0.09
    çļĦçľ¼åħī
    -0.09
    азв
    -0.09
    èĦĤèĤª
    -0.09
    POSITIVE LOGITS
    è¸ı
    0.15
    éŀĭ
    0.14
     shoes
    0.13
    èĦļ
    0.13
    éŀĭåŃIJ
    0.13
    趾
    0.13
    å±¥
    0.13
    è¸Ŀ
    0.12
    踩
    0.12
    éĿ´
    0.11
    Activations Density 0.048%

    No Known Activations